Dimensionality Reduction and Visualization of Bharatanatyam Mudras

Cultural dances are practiced all over the world. The study of various gestures of the performer using computer vision techniques can help in better understanding of these dance forms and for annotation purposes. Bharatanatyam is a classical dance that originated in South India. Bharatanatyam performer uses hand gestures (mudras), facial expressions and body movements to communicate to the audience the intended meaning. According to Natyashastra, a classical text on Indian dance, there are 28 Asamyukta Hastas (single-hand gestures) and 23 Samyukta Hastas (Double-hand gestures) in Bharatanatyam. Open datasets on Bharatanatyam dance gestures are not presently available. An exhaustive open dataset comprising of various mudras in Bharatanatyam was created. The dataset consists of 15[Formula: see text]396 distinct single-hand mudra images and 13[Formula: see text]035 distinct double-hand mudra images. In this paper, we explore the dataset using various multidimensional visualization techniques. PCA, Kernel PCA, Local Linear Embedding, Multidimensional Scaling, Isomap, t-SNE and PCA–t-SNE combination are being investigated. The best visualization for exploration of the dataset is obtained using PCA–t-SNE combination.

Research on Multidimensional Image Intelligent Matching Algorithm of Artificial Intelligence Image Recognition Technology

Image matching is a method of matching by analyzing the gray scale and texture information of the reference image and the image to be matched. Firstly, the scale invariant feature transform (SIFT) algorithm has long descriptor time and poor real time, a nonlinear dimension reduction method (LLE) based on local linear embedding is proposed to preserve the nonlinear information in the original data space as much as possible, shorten the running time of the algorithm, and improve the matching accuracy. Second, aiming at the problem that the Euclidean distance takes a large amount of calculation in the matching process, Manhattan distance is proposed to calculate the similarity between the reference image and the image to be matched, so as to further reduce the algorithm time. Through the improved LLE-SIFT algorithm, experimental results show that the algorithm has a high matching rate and improves the matching speed.

Analysis of Feasibility Modeling of Multimode Physical Fitness Training for Long-Distance Runners

Because the traditional multimode feasibility modeling analysis method of physical fitness training for long-distance runners has the problems of long modeling time and low modeling accuracy, a new multimode feasibility modeling analysis method for physical fitness training of long-distance runners is proposed. The improved LLE (local linear embedding) method is used to reduce the dimensionality of the training data for the physical fitness of long-distance runners. According to the processing results, the information theory is used to analyze the information content of the physical fitness training features of the long-distance runners, the information entropy of each feature is calculated, and the long-distance runners are extracted. Athlete’s physical fitness enhancement training characteristics, combined with quantitative regression analysis method to carry out the information regression analysis of the long-distance runners’ physical fitness training multimode statistical sequence, construct the feasibility evaluation model of the long-distance runners’ physical fitness training multimode and complete the feasibility of the long-distance runners’ physical fitness training multimode feasibility study Mode analysis. The simulation experiment results show that the proposed method has higher accuracy and shorter modeling time for multimode feasibility modeling of physical fitness training for long-distance runners.

Dimensionality reduction of tensor data based on local linear embedding and mode product

There are three contributions in this paper. (1) A tensor version of LLE (short for Local Linear Embedding algorithm) is deduced and presented. LLE is the most famous manifold learning algorithm. Since its proposal, various improvements to LLE have kept emerging without interruption. However, all these achievements are only suitable for vector data, not tensor data. The proposed tensor LLE can also be used a bridge for various improvements to LLE to transfer from vector data to tensor data. (2) A framework of tensor dimensionality reduction based on tensor mode product is proposed, in which the mode matrices can be determined according to specific criteria. (3) A novel dimensionality reduction algorithm for tensor data based on LLE and mode product (LLEMP-TDR) is proposed, in which LLE is used as a criterion to determine the mode matrices. Benefiting from local LLE and global mode product, the proposed LLEMP-TDR can preserve both local and global features of high-dimensional tenser data during dimensionality reduction. The experimental results on data clustering and classification tasks demonstrate that our method performs better than 5 other related algorithms published recently in top academic journals.

Improved weighted local linear embedding algorithm based on Laplacian eigenmaps

To solve the shortcomings of local linear embedding (LLE), such as sensitive to noise and poor generalization ability for new samples, an improved weighted local linear embedding algorithm based on Laplacian eigenmaps (IWLLE-LE) is proposed in this paper. In the proposed algorithm, Laplacian eigenmaps are used to reconstruct the objective function of dimensionality reduction. The weights of it are introduced by combining the geodesic distance with Euclidean distance, which can effectively represent the manifold structure of nonlinear data. Compared the existing LLE algorithm, the proposed one better maintains the original manifold structure of the data. The merit of the proposal is enhanced by the theoretical analysis and numerical experiments, where the classification recognition rate is 2%–8% higher than LLE.

Hierarchical mining algorithm for high dimensional spatiotemporal big data based on association rules

The traditional data mining algorithm focuses too much on a single dimension of data time or space, ignoring the association between time and space, which leads to a large amount of computation and low processing efficiency of the mining algorithm and makes it difficult to guarantee the final data mining effect. In response to the above problems, a hierarchical mining algorithm based on association rules for high-dimensional spatio-temporal big data is proposed. Based on the traditional association rules, after establishing the association rules of spatio-temporal data, the data to be mined are cleaned for redundancy. After selecting the local linear embedding algorithm to reduce the dimensionality of the data, a hierarchical mining strategy is developed to realize high-dimensional spatio-temporal big data mining by searching frequent predicates to form a spatio-temporal transaction database. The simulation experiment results verify that the algorithm has high complexity and can effectively reduce the processing volume, which can improve the processing efficiency by at least 56.26% compared with other algorithms.